杨豪
d15b3c5b43
- src/: 最终交付物（solve.py base64 API、method_l_shape.py 核心算法、verify_result.py 验证工具） - docs/: 方案文档与实验演进记录 - try/: 历史实验脚本（A~K 方法） - 10/10 样本求解成功，3 个独立真值锚点偏差 <=4px
123 lines
4.4 KiB
Python
123 lines
4.4 KiB
Python
"""方法A基线：蒙版多尺度模板匹配（NCC）。
|
|
|
|
对每对样本：
|
|
- 单尺度 1.0：无蒙版 / 有蒙版 —— 验证"裸匹配是否够用"
|
|
- 多尺度 0.50~1.50（步长 0.05，有蒙版）：记录每尺度最佳分数，看目标是否为"唯一精确匹配峰"
|
|
- 可视化：最佳匹配框 + 响应热力图 → try/out/A/
|
|
"""
|
|
from pathlib import Path
|
|
import cv2
|
|
import numpy as np
|
|
|
|
ROOT = Path(__file__).resolve().parent.parent
|
|
CAP = ROOT / "captchas"
|
|
OUT = ROOT / "try" / "out" / "A"
|
|
OUT.mkdir(parents=True, exist_ok=True)
|
|
|
|
SCALES = np.arange(0.50, 1.51, 0.05)
|
|
|
|
|
|
def load_mark(path):
|
|
"""返回 (BGR, alpha)，缺 alpha 时返回全 255。"""
|
|
try:
|
|
m = cv2.imread(str(path), cv2.IMREAD_UNCHANGED)
|
|
if m is None or m.ndim < 2:
|
|
return None, None
|
|
if m.ndim == 3 and m.shape[2] == 4:
|
|
return m[..., :3].copy(), m[..., 3].copy()
|
|
return m.copy(), np.full(m.shape[:2], 255, np.uint8)
|
|
except Exception as e:
|
|
print(f" mark 读取失败: {e}")
|
|
return None, None
|
|
|
|
|
|
def match_masked(big, bgr, alpha, scale):
|
|
"""缩放模板与蒙版后做 CCORR_NORMED 匹配。返回 (score, loc, res)。"""
|
|
try:
|
|
if abs(scale - 1.0) < 1e-9:
|
|
tpl, mask = bgr, alpha
|
|
else:
|
|
w = max(8, round(bgr.shape[1] * scale))
|
|
h = max(8, round(bgr.shape[0] * scale))
|
|
if w >= big.shape[1] or h >= big.shape[0]:
|
|
return -1.0, (0, 0), None
|
|
tpl = cv2.resize(bgr, (w, h), interpolation=cv2.INTER_AREA)
|
|
mask = cv2.resize(alpha, (w, h), interpolation=cv2.INTER_AREA)
|
|
res = cv2.matchTemplate(big, tpl, cv2.TM_CCORR_NORMED,
|
|
mask=mask.astype(np.float32) / 255.0)
|
|
res = np.nan_to_num(res, nan=-1.0, posinf=-1.0, neginf=-1.0).astype(np.float32)
|
|
_, score, _, loc = cv2.minMaxLoc(res)
|
|
return float(score), loc, res
|
|
except cv2.error as e:
|
|
print(f" 匹配失败(scale={scale}): {e}")
|
|
return -1.0, (0, 0), None
|
|
|
|
|
|
def heatmap_png(res):
|
|
r = res.copy()
|
|
r -= r.min()
|
|
if r.max() > 0:
|
|
r /= r.max()
|
|
return cv2.applyColorMap((r * 255).astype(np.uint8), cv2.COLORMAP_JET)
|
|
|
|
|
|
def process_pair(name):
|
|
try:
|
|
big = cv2.imread(str(CAP / f"{name}.jpeg"), cv2.IMREAD_COLOR)
|
|
if big is None:
|
|
print(f"{name[:12]} 大图读取失败")
|
|
return
|
|
bgr, alpha = load_mark(CAP / f"{name}-mark.png")
|
|
if bgr is None:
|
|
print(f"{name[:12]} mark 读取失败")
|
|
return
|
|
|
|
# 单尺度对照
|
|
res0 = cv2.matchTemplate(big, bgr, cv2.TM_CCOEFF_NORMED)
|
|
_, s0, _, l0 = cv2.minMaxLoc(res0)
|
|
s1, l1, _ = match_masked(big, bgr, alpha, 1.0)
|
|
|
|
# 多尺度扫描
|
|
scores, locs = [], []
|
|
for sc in SCALES:
|
|
sco, loc, _ = match_masked(big, bgr, alpha, float(sc))
|
|
scores.append(sco)
|
|
locs.append(loc)
|
|
curve = np.array(scores)
|
|
k = int(curve.argmax())
|
|
best_scale = float(SCALES[k])
|
|
best_score, best_loc = float(curve[k]), locs[k]
|
|
masked = curve.copy()
|
|
masked[max(0, k - 1): k + 2] = -1.0
|
|
second = float(masked.max())
|
|
|
|
print(f"{name[:12]} 裸1.0={s0:.3f}@{l0} 蒙版1.0={s1:.3f}@{l1} "
|
|
f"最佳尺度={best_scale:.2f} 分数={best_score:.3f} 次峰={second:.3f} "
|
|
f"峰谷差={float(curve.max() - curve.min()):.3f}")
|
|
|
|
# 可视化：匹配框 + 最佳尺度响应热力图
|
|
_, _, res_best = match_masked(big, bgr, alpha, best_scale)
|
|
vis = big.copy()
|
|
w = max(8, round(bgr.shape[1] * best_scale))
|
|
h = max(8, round(bgr.shape[0] * best_scale))
|
|
cv2.rectangle(vis, best_loc, (best_loc[0] + w, best_loc[1] + h), (0, 0, 255), 2)
|
|
cv2.putText(vis, f"s={best_scale:.2f} {best_score:.2f}",
|
|
(best_loc[0], max(12, best_loc[1] - 4)),
|
|
cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 255), 1)
|
|
cv2.imwrite(str(OUT / f"{name[:12]}-match.png"), vis)
|
|
if res_best is not None:
|
|
cv2.imwrite(str(OUT / f"{name[:12]}-heat.png"), heatmap_png(res_best))
|
|
except Exception as e:
|
|
print(f"{name[:12]} 处理失败: {e}")
|
|
|
|
|
|
def main():
|
|
pairs = sorted({p.name.replace("-mark.png", "") for p in CAP.glob("*-mark.png")})
|
|
for name in pairs:
|
|
process_pair(name)
|
|
print(f"\n结果图已写入 {OUT}/")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|